JMIR Medical Education

Accurate medical advice is paramount in ensuring optimal patient care, and misinformation can lead to misguided decisions with potentially detrimental health outcomes. The emergence of Large Language Models (LLMs) such as OpenAI's GPT-4 has spurred interest in their potential healthcare applications, particularly in automated medical consultation. Yet, rigorous investigations comparing their performance to human experts remain sparse.

The introduction of Chat-GPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out; however, our study aimed to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot.

Multiple-choice examinations are frequently employed among German dental schools. However, details regarding the used item types and applied scoring methods are lacking.

The continued demand for digital health requires that providers adapt thought processes to enable sound clinical decision making in digital settings. Providers report that lack of training is a barrier to providing digital healthcare. Physical exam techniques and hands-on interventions must be adjusted in safe, reliable and feasible ways to digital care and decision making may be impacted by modifications made to these techniques. We have proposed a framework for determining if a procedure can be modified to obtain a comparable result in a digital environment or if a referral to in-person care is required. The decision making framework developed using program outcomes of a digital physical therapy platform, and aims to alleviate provider barriers to providing digital care. This paper describes the unique considerations a provider must make when collecting background information, selecting procedures, executing procedures, assessing results, and determining if they can proceed with clinical care in digital settings.

Over the last decade, there has been growing interest in inverted classroom teaching (ICT) and its various forms within the education sector. Physiology is a core course that bridges basic and clinical medicine, and inverted classrooms teaching in physiology (ITP) has been sporadically practiced to different extents globally. However, students' and teachers' responses and feedback to ITP are diverse, and the effectiveness of modified ITP integrated into regular teaching is difficult to assess objectively and quantitively.

The persistence of diagnostic errors, despite advances in medical knowledge and diagnostics, highlights the importance of understanding atypical disease presentations and their contribution to mortality and morbidity. Artificial intelligence (AI), particularly Generative Pre-trained Transformers like ChatGPT-4, holds promise for improving diagnostic accuracy, but requires further exploration in handling atypical presentations.

Background: A significant component of Canadian medical education is the development of clinical skills. The medical educational curriculum assesses these skills through the Objective Structured Clinical Examination (OSCE). The OSCE assesses skills imperative to good clinical practice, such as patient communication, clinical decision-making and medical knowledge. Despite the widespread implementation of this examination across all academic settings, few preparatory resources currently exist that cater specifically to Canadian medical students. MonkeyJacket is a novel, open-access, online application built with the goal of providing medical students with an accessible and representative tool for clinical skill development for the OSCE and clinical settings. Viewpoint: This paper represents the development of the MonkeyJacket application and its potential to assist medical students in preparation for clinical exams and practical settings. Aim Statement: Limited resources exist that are virtual, accessible in cost, specific to the Medical Council of Canada (MCC), and most importantly, scalable in nature. The goal of this research study is to thoroughly describe the potential utility of the application, particularly in its capacity to provide practice and scalable formative feedback to medical students. Development: MonkeyJacket was developed to allow Canadian medical students the opportunity to practice their clinical examination skills and receive peer feedback using a centralized platform. The OSCE cases included in the application were developed using the MCC guidelines to ensure their applicability to a Canadian setting. There are currently 75 cases covering five specialties, including cardiology, respirology, gastroenterology, neurology, and psychiatry. Application Interface and Features: The MonkeyJacket application is an online platform that allows medical students to practice clinical decision-making skills in real-time with their peers through a synchronous platform. Through this application, students can practice patient interviewing, clinical reasoning, developing differential diagnoses, formulating a management plan, and they can receive both qualitative and quantitative feedback. Each clinical case is associated with an ‘assessment checklist’ that is accessible to students after practice sessions are complete in order to promote personal improvement through peer feedback. This tool provides students with relevant case stems, follow-up questions to probe for differential diagnoses and management plans, assessment checklists, and the ability to review the trend in their performance. Conclusions: The MonkeyJacket application provides medical students with a valuable tool that promotes clinical skill development for OSCEs and clinical settings. MonkeyJacket introduces a way for medical learners to receive feedback regarding patient interviewing and clinical reasoning skills that is both formative and scalable in nature, in addition to promoting inter-institutional learning. The widespread usage of this application can increase practice and feedback of clinical skills amongst medical learners. This will not only benefit the learner, but more importantly, can provide downstream benefits for the most valuable stakeholder in medicine - the patient.

Massive Open Online Courses (MOOCs) are increasingly used to educate healthcare workers during public health emergencies. Early in 2020, the World Health Organization (WHO) developed a series of MOOCs for COVID-19, introducing the disease and strategies to control its outbreak, with six courses specifically targeting healthcare workers as learners. In 2020, Stanford University also launched a MOOC designed to deliver accurate and timely education on COVID-19 equipping healthcare workers across the globe to provide healthcare safely and effectively to patients suffering from the novel infectious disease. While the use of MOOCs for just-in-time training has expanded during the pandemic, evidence is limited regarding the factors motivating healthcare workers to enroll in and complete courses, particularly in low- and lower-middle-income countries (LICs/LMICs).

A momentous amount of health data has been and is being collected. Across all levels of healthcare, data is driving decision making and impacting patient care. A new knowledge and role for those in healthcare is emerging – the need for a health data informed workforce. In this commentary, the authors describe approaches needed to build a health data informed workforce, a new and critical skill for the healthcare ecosystem.

The integration of chatbots in nursing education is a rapidly evolving area with potential transformative impacts. This narrative review aims to synthesize and analyze the existing literature on chatbots in nursing education.

The increasing significance of artificial intelligence (AI) in healthcare has generated an increasing need for healthcare professionals to possess a comprehensive understanding of AI technologies, requiring an adaptation in medical education.

Healthcare professionals must learn continuously as a core part of their work. As the rate of knowledge production in biomedicine increases, better support for providers’ continuous learning is needed. In health systems, feedback is pervasive and is widely considered to be essential for learning that drives improvement. Clinical quality dashboards are one widely-deployed approach to delivering feedback, but engagement with these systems is commonly low, reflecting a limited understanding of how to improve the effectiveness of feedback about health care. When coaches and facilitators deliver feedback for improving performance, they aim to be responsive to the recipient’s motivations, information needs, and preferences. However, such functionality is largely missing from dashboards and feedback reports. Precision feedback is the delivery of high-value, motivating performance information that is prioritized based on its motivational potential for a specific recipient, including their needs and preferences. Anesthesia care offers a clinical domain with high-quality performance data and an abundance of evidence-based quality metrics.